© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18947
    Prev
    Next
    INDEX
    Explanations

    explaining subsequent phrases

    np_acts-logits-general · gemini-2.5-flash-lite

    happens because, happens when

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    тири
    0.46
     entrusted
    0.43
     originally
    0.43
    示例
    0.41
    }=[
    0.40
     ويمكن
    0.40
    пев
    0.40
     ，
    0.40
     പിന്തുണ
    0.39
     unsurprisingly
    0.39
    POSITIVE LOGITS
     জায়গায়
    0.44
    あなたが
    0.44
     fru
    0.41
    澗
    0.41
    ード
    0.40
     مشا
    0.40
     মাঝামা
    0.40
     भिख
    0.40
     cellules
    0.39
     bloating
    0.39
    Activations Density 0.000%

    No Known Activations